Visual event recognition in videos by learning from web data

By Lixin Duan, Dong Xu, Ivor Wai-Hung Tsang, Jiebo Luo. 2010

437 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Unsupervised Domain Adaptation with Residual Transfer Networks (2016, background): “Codes and datasets will be available at https://github.com/thuml/transfer-caffe.”
Efficient Learning of Domain-invariant Image Representations (2013, methodology): “Several SVMbased approaches have been proposed for image domain adaptation, including: weighted combination of source and target SVMs and transductive SVMs applied to adaptation in [21]; the feature replication method of [17]; Adaptive SVM [8, 9], where the source model parameters are adapted by add”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “webly supervised approaches [271, 272, 273, 274, 158, 159, 275] are also related to DA and HDA as is these approaches rely on collected Web data (source) data used to reﬁne the target model. As such, [276] uses multiple kernel learning to adapt visual events learned from the Web data for video clips”
Learning with Augmented Features for Heterogeneous Domain Adaptation (2012, methodology): “used for diﬀerent research ﬁelds such as natural language processing and computer vision (Blitzer et al., 2006; 2007; Daum´e III, 2007; Duan et al., 2010; 2012b;a; Wu & Dietterich, 2004).”
Domain Adaptive Faster R-CNN for Object Detection in the Wild (2018, methodology): “Conventional methods include domain transfer multiple kernel learning [10, 11], asymmetric metric learning [33], subspace interpolation [23], geodesic flow kernel [22], subspace alignment [14], covariance matrix alignment [52, 57], etc.”
Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization (2015, background): “from source or auxiliary domains [35], [36], [37], [38], [39].”
A Survey on Ambient Intelligence in Health Care (2013, neutral): “Other modalities that have been researched for activity recognition include video cameras [58], [59], [60], [61], microphones [62], [63], and GPS locators [64], [65].”
One-Pass Learning with Incremental and Decremental Features (2016, background): “Another related learning paradigm is transfer learning [20], [21], [22], [23], [24], [25].”
Where am I in the dark: Exploring active transfer learning on the use of indoor localization based on thermal imaging (2016, background): “[45] extended the above target decision function as”
Tabula rasa: Model transfer for object category detection (2011, background): “There is another school of transfer learning where classifiers are transferred between domains [3, 4, 20, 28], for example by learning feature distributions for the source and target domains, but we are not concerned with this type of domain transfer problem here.”
Geodesic flow kernel for unsupervised domain adaptation (2012, background): “Beyond image recognition, mismatched training and testing conditions are also abundant: in other computer vision tasks [10, 28, 19, 11], speech and language processing [21, 4, 5], and others.”
Recognizing RGB Images by Learning from RGB-D Data (2014, methodology): “Meanwhile, to cope with the considerable variation in feature distributions, new domain adaptation methods were recently developed for different computer vision applications [15, 22, 14, 16, 7, 6, 10, 8, 13, 1].”
Feature-based transfer learning with real-world applications (2010, background): “Applications of transfer learning in these fields include image classification [202, 158, 185, 218, 161, 94, 177], image retrieval [73, 115, 38], face verification from images [196], age estimation from facial images [225], image semantic segmentation [190], video retrieval [208, 73], video concept ”
Semantic Pooling for Complex Event Analysis in Untrimmed Videos (2016, background): “Event detection refers to the task in which a learning algo-rithm must rank a large number of unseen videos according to their likelihood of containing an event of interest [18].”
Domain Generalization and Adaptation Using Low Rank Exemplar SVMs (2018, methodology): “[4] proposed Adaptive MKL based on multiple kernel learning (MKL), and a multi-domain adaptation method by selecting the most relevant source domains [19].”
Web-Based Classifiers for Human Action Recognition (2012, background): “[28] leverage large amounts of Web videos for visual event recognition.”
Transfer Learning with Label Noise (2017, background): “Further, in computer vision, collecting a labeled visual recognition dataset is expensive but it is easy to access a large number of loosely labeled web images and videos [5].”